Advances in diagnostic techniques are necessary since breast cancer is a major worldwide health concern. The purpose of this project is to improve the accuracy and efficiency of breast cancer detection by utilizing machine learning, more especially logistic regression. The fine needle aspiration (FNA) pictures in the collection are the source of several important properties, including fractal size, smoothness, compactness, concavity, concave spots, symmetry, and mean radius. Through statistical analysis, exploratory data exploration, and preprocessing procedures, a thorough knowledge of the dataset may be attained. We go into great depth on the training and assessment procedures of the logistic regression model in the following sections. Evaluating the correctness of the model on both training and test datasets yields a performance score. The research yielded a prediction system that illustrates the practical applications of the created logistic regression model for breast cancer diagnosis. The discussion over the use of machine learning to medical diagnosis—especially breast cancer diagnosis—continues with this work. With further research, these findings may improve current diagnostic procedures and provide a more sophisticated, data-driven method of detecting breast cancer.